package iace

import "sort"

// Evidence / citation layer for the risk-frequency anchors. Each entry is an
// aggregate, permissively-licensed public statistic (Eurostat ESAW, CC BY 4.0)
// that anchors the RELATIVE ordering of a contact mode's probability tier. The
// tier VALUES in contactModeTable are BreakPilot's own GT-calibrated numbers —
// this table only carries the provenance so generated risk numbers are
// auditable and correctly attributed. No raw dataset is vendored; only these
// aggregate facts. Excluded by license: DGUV, DIN/Beuth/ISO/IEC. See
// DATA_SOURCES.md. RAG/Qdrant ingestion is deliberately NOT used here: ~a dozen
// stable aggregate facts are better served by a license-tagged code table than
// by vector retrieval.

// RiskEvidence is the public-statistics provenance for one contact mode.
type RiskEvidence struct {
	Mode        string `json:"mode"`
	Label       string `json:"label"`       // German contact-mode label
	Stat        string `json:"stat"`        // the cited aggregate figure
	Source      string `json:"source"`      // "Eurostat (ESAW)"
	License     string `json:"license"`     // "CC BY 4.0"
	Attribution string `json:"attribution"` // ready-to-print citation line
	Retrieved   string `json:"retrieved"`   // retrieval month
}

const (
	esawSource      = "Eurostat (ESAW)"
	esawLicense     = "CC BY 4.0"
	esawAttribution = "Quelle: Eurostat (ESAW), CC BY 4.0"
	esawRetrieved   = "2026-06"
)

func esawEvidence(mode, label, stat string) RiskEvidence {
	return RiskEvidence{Mode: mode, Label: label, Stat: stat, Source: esawSource,
		License: esawLicense, Attribution: esawAttribution, Retrieved: esawRetrieved}
}

// contactModeEvidence holds only the contact modes for which a specific public
// figure is documented; other modes are anchored by the ESAW ordering and
// GT-calibrated without a single citable share, so they carry no fabricated stat.
var contactModeEvidence = map[string]RiskEvidence{
	"impact_stationary": esawEvidence("impact_stationary", "Anstoßen an ruhendem Objekt", "~24 % der Arbeitsunfälle"),
	"struck_by":         esawEvidence("struck_by", "Getroffen von bewegtem Objekt", "~13 % (nicht-tödlich) / ~24 % (tödlich)"),
	"crushing":          esawEvidence("crushing", "Quetschen / Einklemmen", "~14 % der tödlichen Arbeitsunfälle"),
	"cutting":           esawEvidence("cutting", "Kontakt mit scharfem Gegenstand", "~15 % der Arbeitsunfälle"),
}

// RiskEvidenceFor returns the documented public statistic for a contact mode.
func RiskEvidenceFor(mode string) (RiskEvidence, bool) {
	e, ok := contactModeEvidence[mode]
	return e, ok
}

// AllRiskEvidence returns the full evidence register (sorted), for a
// "Datenquellen" panel / risk-assessment export attribution.
func AllRiskEvidence() []RiskEvidence {
	out := make([]RiskEvidence, 0, len(contactModeEvidence))
	for _, e := range contactModeEvidence {
		out = append(out, e)
	}
	sort.Slice(out, func(i, j int) bool { return out[i].Mode < out[j].Mode })
	return out
}

// RiskDataSourcesNote is the overall attribution shown wherever engine risk
// numbers appear, satisfying the ESAW CC BY 4.0 source-acknowledgement.
const RiskDataSourcesNote = "Häufigkeits-/Wahrscheinlichkeits-Tiers verankert am öffentlichen Kontaktmodus-Ranking von " +
	esawSource + " (" + esawLicense + "), kalibriert an BreakPilot-Ground-Truth. Keine Norm-Tabelle reproduziert; DGUV/DIN/ISO ausgeschlossen."